Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/53716
Title: New approaches to solve the local minimum problem and improve the classification ability of learning algorithms in multi-layer feed-forward neural networks
Authors: Xu, Shensheng
Advisors: Cheung, Lawrence Chi-chung (EIE)
Keywords: Neural networks (Computer science)
Computer algorithms.
Issue Date: 2016
Publisher: The Hong Kong Polytechnic University
Abstract: This thesis proposes two new algorithms. They are Wrong Output Modification (WOM) and Threshold of Output Differences (TOD). WOM is used to solve the local minimum problem in training a multi-layer feed-forward network while TOD is used to improve the classification ability in training a multi-layer feed-forward network. When a searching to find a global minimum is trapped by a local minimum, the change of weights could be zero or extremely small. Thus, the mean square error cannot be further reduced while its value is still so large that the searching cannot find the global minimum. In this circumstance, WOM locates the wrong output values and moves them closer to their corresponding target output values. Thus neuron weights are modified accordingly, and hence the searching can escape from such local minimum. WOM can be applied in different learning algorithms. Our performance investigation shows that learning with WOM can always escape from local minima and converge to a global minimum. Moreover, it obtains better classification ability after training. TOD monitors the difference of each output value and its corresponding target output value. All differences are used to identify whether a searching finds a global minimum or not. TOD can be applied in different learning algorithms. Our performance investigation shows that by using TOD, a multi-layer feed-forward neural network can be trained in a better way so that its classification ability is better. This improvement is very significant if all features in testing data can be found in training data.
Description: PolyU Library Call No.: [THS] LG51 .H577M EIE 2016 Xu
ix , 78 pages :illustrations
URI: http://hdl.handle.net/10397/53716
Rights: All rights reserved.
Appears in Collections:Thesis

Files in This Item:
File Description SizeFormat 
b28906317_link.htmFor PolyU Users208 BHTMLView/Open
b28906317_ira.pdfFor All Users (Non-printable)815.07 kBAdobe PDFView/Open
Show full item record

Page view(s)

95
Last Week
4
Last month
Checked on Dec 11, 2017

Download(s)

16
Checked on Dec 11, 2017

Google ScholarTM

Check



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.